research-layer-aggregate
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-06-13
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- id
- research-layer-aggregate
- title
- Layer Aggregation
03 SKILL.md 正文
Layer Aggregation
Synthesize findings from layer phases and produce actionable outputs for the next layer.
Process
- Extract key findings — identify the 3-5 most important discoveries
- Select promising areas — from prior identification, select top areas for next layer
- Quality gate check — verify minimum threshold is met
- Document dropped areas — rationale for deprioritization
- Generate insight triggers — what must be investigated in next layer:
- Contradictions: findings that conflict and need resolution
- Weak evidence: claims needing stronger support
- Scope expansion: areas more complex than expected
- Confirmations: expected findings validated
- Make recommendation — proceed to next layer or terminate
Insight Triggers
| Type | Description | Effect on Next Layer |
|---|---|---|
contradiction |
Finding contradicts other findings | Must investigate and resolve |
weakEvidence |
Claim has insufficient support | Must find stronger sources |
scopeExpansion |
Area more complex than expected | Expand investigation scope |
confirmation |
Expected finding validated | Document and move focus elsewhere |
deadEnd |
Area explored but unproductive | Drop from further investigation |
Quality Gate Criteria
- Layer 1: ≥3 promising areas (else terminate)
- Layer 2: cross-area insights produced (else skip Layer 3)
- Layer 3: definitive synthesis achieved (else document limitations)
Quality Criteria
- All key findings have source citations
- Promising areas have explicit evidence strength scoring
- At least 1 insight trigger generated
- Quality gate check is explicit and documented
- Recommendation is valid (proceed_to_layer_N or terminate/skip)
04 同仓库更多 Skills
hello-checker
Use this skill when asked to "verify", "check", or "validate" a file's existence and content. It provides a reliable workflow for confirming files meet their spec.
ask-skill
暂无简介
html-review-artifact
Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML
converge-planning
Design a Converge playbook end-to-end. Use when the user says "plan a project", "design a playbook", "decompose into tasks", "scaffold a Converge workflow", "onboard to Converge", or asks how to write TASK.md / playbook.yml. Two entry points: plan a new playbook or update an existing one. Hand off to `/converge-control` after producing the playbook structure.
converge-control
Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says "run my playbook", "execute this", "monitor the run", "converge failed", "the run is stuck", "retry failures", "babysit this playbook", "what's the status?", "show me the gantt", or asks how to use `converge run` / `--select` / `inspect` / `doctor` / `clean` / `stop`. Also use it for `HTTP 401` / `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.
repair-taskts
Fix task.ts definition issues — Seed syntax, missing .build(), empty checks, import errors, TypeScript errors